Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing

A challenge to modeling and monitoring the health of the ocean environment is that it is largely under sensed and difficult to sense remotely. Autonomous underwater vehicles (AUVs) can improve observability, for example of algal bloom regions, ocean acidification, and ocean circulation. This AUV par...

Full description

Bibliographic Details
Main Authors: Li, Hui, Williams, Brian
Format: Article in Journal/Newspaper
Language:English
Published: Association for the Advancement of Artificial Intelligence 2011
Subjects:
Online Access:https://ojs.aaai.org/index.php/AAAI/article/view/7800
id ftjaaai:oai:ojs.aaai.org:article/7800
record_format openpolar
spelling ftjaaai:oai:ojs.aaai.org:article/7800 2023-05-15T17:51:10+02:00 Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing Li, Hui Williams, Brian 2011-08-04 application/pdf https://ojs.aaai.org/index.php/AAAI/article/view/7800 eng eng Association for the Advancement of Artificial Intelligence https://ojs.aaai.org/index.php/AAAI/article/view/7800/7659 https://ojs.aaai.org/index.php/AAAI/article/view/7800 Copyright (c) 2021 Proceedings of the AAAI Conference on Artificial Intelligence Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 25 No. 1 (2011): Twenty-Fifth AAAI Conference on Artificial Intelligence; 1365-1370 2374-3468 2159-5399 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Peer-reviewed Article 2011 ftjaaai 2022-07-02T23:26:54Z A challenge to modeling and monitoring the health of the ocean environment is that it is largely under sensed and difficult to sense remotely. Autonomous underwater vehicles (AUVs) can improve observability, for example of algal bloom regions, ocean acidification, and ocean circulation. This AUV paradigm, however, requires robust operation that is cost effective and responsive to the environment. To achieve low cost we generate operational sequences automatically from science goals, and achieve robustness by reasoning about the discrete and continuous effects of actions. We introduce Kongming2, a generative planner for hybrid systems with temporally extended goals (TEGs) and temporally flexible actions. It takes as input high level goals and outputs trajectories and actions of the hybrid system, for example an AUV. Kongming2 makes two major extensions to Kongming1: planning for TEGs, and planning with temporally flexible actions. We demonstrated a proof of concept of the planner in the Atlantic ocean on Odyssey IV, an AUV designed and built by the MIT AUV Lab at Sea Grant. Article in Journal/Newspaper Ocean acidification AAAI Publications (Association for the Advancement of Artificial Intelligence)
institution Open Polar
collection AAAI Publications (Association for the Advancement of Artificial Intelligence)
op_collection_id ftjaaai
language English
description A challenge to modeling and monitoring the health of the ocean environment is that it is largely under sensed and difficult to sense remotely. Autonomous underwater vehicles (AUVs) can improve observability, for example of algal bloom regions, ocean acidification, and ocean circulation. This AUV paradigm, however, requires robust operation that is cost effective and responsive to the environment. To achieve low cost we generate operational sequences automatically from science goals, and achieve robustness by reasoning about the discrete and continuous effects of actions. We introduce Kongming2, a generative planner for hybrid systems with temporally extended goals (TEGs) and temporally flexible actions. It takes as input high level goals and outputs trajectories and actions of the hybrid system, for example an AUV. Kongming2 makes two major extensions to Kongming1: planning for TEGs, and planning with temporally flexible actions. We demonstrated a proof of concept of the planner in the Atlantic ocean on Odyssey IV, an AUV designed and built by the MIT AUV Lab at Sea Grant.
format Article in Journal/Newspaper
author Li, Hui
Williams, Brian
spellingShingle Li, Hui
Williams, Brian
Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing
author_facet Li, Hui
Williams, Brian
author_sort Li, Hui
title Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing
title_short Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing
title_full Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing
title_fullStr Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing
title_full_unstemmed Hybrid Planning with Temporally Extended Goals for Sustainable Ocean Observing
title_sort hybrid planning with temporally extended goals for sustainable ocean observing
publisher Association for the Advancement of Artificial Intelligence
publishDate 2011
url https://ojs.aaai.org/index.php/AAAI/article/view/7800
genre Ocean acidification
genre_facet Ocean acidification
op_source Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 25 No. 1 (2011): Twenty-Fifth AAAI Conference on Artificial Intelligence; 1365-1370
2374-3468
2159-5399
op_relation https://ojs.aaai.org/index.php/AAAI/article/view/7800/7659
https://ojs.aaai.org/index.php/AAAI/article/view/7800
op_rights Copyright (c) 2021 Proceedings of the AAAI Conference on Artificial Intelligence
_version_ 1766158228864892928